KR101921709B1 - System for object tracking using muli-camera unit - Google Patents

Abstract

The present invention relates to an object recognition system using a multi-camera unit implemented to track a plurality of performers using a plurality of (IR) cameras and to enhance the accuracy of tracker tracking, A stage for demonstration; A plurality of cameras installed toward the stage for recognizing an identification mark in the performance space; An IR marker attached to a part of the performer body and recognized by the camera; And a control unit for receiving the recognized IR marker sensing value from the cameras and for recognizing and tracking the position of the performer according to the IR marker sensing value, the control unit comprising: ; And allocates two or more cameras to be used for recognizing and tracking the performers for each zone according to the recognition rates of the cameras for the respective zones. According to the present invention, in the present invention, a plurality of multi-IR cameras are used to identify / track user locations in a performance space, distinguish the performance spaces, recognize and recognize objects through IR camera combination, So that the position of the performer can be accurately grasped.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to an object recognition system using a multi-

The present invention relates to an object recognition system using a multi-camera unit, which is implemented in a system for distinguishing and tracking performers, in which multiple performers are trekked using a plurality of IR cameras, It is the invention of the result that is produced in carrying out the task of 'Taekwondo action performance sports technology development' among the sports industry technology establishment project of the Ministry of Sports and Tourism.

Recently, with the rapid development of multimedia environment, various IOT technologies have been applied to performance culture.

Recently, a technique has been developed in which performers participating in performances, various stage devices, and special effects are interacted with each other.

In order to realize such a performance interaction, a technique for discriminating, recognizing, and processing performers performing basically in a physical performance space should be provided.

The present applicant has developed a system capable of interacting with a plurality of participants using a Kinect camera and has been patented (Korean Patent No. 1575063).

However, in the case of the prior art using a Kinect camera. As shown in FIG. 1, although the stability of the user input is secured, the installation cost of the equipment is high, and only limited actions such as touch input are recognized, and the movement range of the user and the interaction action are limited.

On the other hand, although the IR camera has an advantage of recognizing various activities of the user and interacting with the user, the IR camera has a problem that an error occurs in the location and the division of the user due to various factors.

Particularly, in the case of a sports performance having a fast action speed, a plurality of users are participating at the same time, resulting in an error in user identification due to overlapping among users.

Korean Patent No. 1575063

SUMMARY OF THE INVENTION The present invention has been made in order to solve the above problems, and it is an object of the present invention to provide a camera having a high recognition rate for each location, And to provide an object recognition system using a multi-camera unit that can improve the accuracy by tracking and identifying a user's position in combination.

In addition, in recognizing a user in a performance space using a plurality of IR cameras, the present invention recognizes a user by utilizing an IR camera with high tracking accuracy according to the location of a performance space, And an object recognition system using a multi-camera unit capable of improving efficiency.

According to an aspect of the present invention, there is provided a game system comprising: a stage for performing performances while a performer moves; A plurality of cameras installed toward the stage for recognizing an identification mark in the performance space; An IR marker attached to a part of the performer body and recognized by the camera; And a control unit for receiving the recognized IR marker sensing value from the cameras and for recognizing and tracking the position of the performer in accordance with the IR marker sensing value, the control unit comprising: ; And allocates two or more cameras to be used for recognizing and tracking the performers for each zone according to the recognition rates of the cameras for the respective zones.

In addition, the cameras may be disposed so that their installation positions are spaced apart from each other.

The control unit may further include: a communication module receiving the IR marker sensing value of the camera; A control module for storing the sensed values received from the cameras in a database; A calculation module for calculating and correcting the position of the user by identifying the user using a sensing value of the camera stored in the database; And a database for storing sensing values and measurement values received from the camera.

And the recognition rate of the cameras for each zone may be checked by recognizing the identification mark on the identification pad installed on the stage.

At this time, the identification pad may be a pad formed by dividing a region in a lattice form and attaching an identification mark capable of recognizing infrared rays to the respective regions.

On the other hand, the recognition rates of the cameras for each zone may be inspected by recognizing the identification mark on the identification unit installed on the stage where the zones are divided in a lattice form.

At this time, the identification unit includes: a receiving unit; A rotating plate provided on the upper part of the receiving unit perpendicularly to the bottom surface; A driving unit for rotating the rotating plate; And an identification mark attached to one side of the rotary plate.

The driving unit may rotate the rotating plate according to the rotation speed set according to the performance type.

The control module may drive the cameras to recognize the identification mark provided on the object, Receiving an identification marker recognition value of each position for each of the cameras; Calculating a position value of the identification mark according to the recognition value of each camera; The calculated position values may be compared with each other, and the recognition rate of each camera for the corresponding area may be determined according to the difference value from the average value.

The control module may calculate a position value of the identification mark according to the recognition value of the cameras by using a combination of two or more cameras; It is also possible to determine the recognition rate for the corresponding area for each combination of cameras.

In addition, the control module may set a combination of cameras to be used for recognizing and tracking the performer for each zone according to the recognition rate of the combination of cameras for each zone.

In the object recognition system using the multi-camera unit according to the present invention as described above, the following effects can be expected.

That is, according to the present invention, a plurality of multi IR cameras are used to identify / track the user's location in the performance space, and the performance space is divided and the object is recognized / tracked through IR camera combination having a high recognition rate for each area. Can be accurately grasped.

In addition, since each IR camera is physically installed, the recognition rate of each area is checked without the operation of the IR camera, and the IR camera is assigned to each area, so that synchronization error due to the operation of the operator can be prevented There is an effect.

As described above, according to the present invention, accuracy in tracking and identifying a location of a user located in a performance space is ensured, so that an accurate interaction with each user can be performed even though a large number of users participate in the performance space and perform quick operation .

BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 is an illustration showing a method of identifying a plurality of users on a touch device according to the prior art; Fig.
FIG. 2 is an exemplary view showing an example in which an object recognition system according to the present invention is constructed in a performance space; FIG.
3 is a block diagram illustrating a configuration of an object recognition system using a multi-camera unit according to a specific embodiment of the present invention.
4 is a diagram illustrating an example of calculating a recognition rate for each position of a multi-camera unit installed in a performance space according to a specific embodiment of the present invention.
5 is a diagram illustrating an example of calculating a recognition rate for each position of a multi-camera unit installed in a performance space according to another embodiment of the present invention.
FIG. 6 is an exemplary view showing an example of an identification unit applied to another embodiment of the present invention; FIG.
FIG. 7 is a diagram illustrating an object recognition method for each zone in a performance space by reflecting the recognition rate of each camera according to the present invention. FIG.
FIG. 8 is a flowchart illustrating a method of calculating a recognition rate for each position of a multi-camera installed in a performance space according to a specific embodiment of the present invention.

Hereinafter, an object recognition system using a multi-camera unit according to a specific embodiment of the present invention will be described with reference to the accompanying drawings.

BRIEF DESCRIPTION OF THE DRAWINGS The above and other objects, features and advantages of the present invention will be more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which: FIG. The present invention may, however, be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the invention to those skilled in the art. Is provided to fully convey the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS In the following description of the present invention, detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear. , Which may vary depending on the intention or custom of the user, the operator, and the like. Therefore, the definition should be based on the contents throughout this specification.

Each block of the accompanying block diagrams and combinations of steps of the flowcharts may be performed by computer program instructions (execution engines), which may be stored in a general-purpose computer, special purpose computer, or other processor of a programmable data processing apparatus The instructions that are executed through the processor of the computer or other programmable data processing equipment will generate means for performing the functions described in each block or flowchart of the block diagram.

These computer program instructions may also be stored in a computer usable or computer readable memory capable of directing a computer or other programmable data processing apparatus to implement the functionality in a particular manner so that the computer usable or computer readable memory It is also possible for the instructions stored in the block diagram to produce an article of manufacture containing instruction means for performing the functions described in each block or flowchart of the flowchart.

And computer program instructions may be loaded onto a computer or other programmable data processing equipment so that a series of operating steps may be performed on a computer or other programmable data processing equipment to create a computer- It is also possible that the instructions that perform the data processing equipment provide the steps for executing the functions described in each block of the block diagram and at each step of the flowchart.

Also, each block or step may represent a portion of a module, segment, or code that includes one or more executable instructions for executing the specified logical functions, and in some alternative embodiments, It is also possible for functions to occur out of order.

That is, it is also possible that the two blocks or steps shown are actually concurrently performed, and that the blocks or steps are performed in the reverse order of the function as required.

3 is a block diagram illustrating the configuration of an object recognition system using a multi-camera unit according to a specific embodiment of the present invention. FIG. 2 is a block diagram FIG. 4 is a diagram illustrating an example of calculating the recognition rate for each position of a multi-camera unit installed in a performance space according to a specific embodiment of the present invention. FIG. 6 is an exemplary view showing an example of an identification unit applied to another embodiment of the present invention, and FIG. 7 is a view showing an example of a recognition performance of a performance FIG. 8 is a diagram illustrating a method of estimating the recognition rate of a multi-camera installed in a performance space according to a specific embodiment of the present invention. A time limit flowchart.

An object recognition system using a multi-camera unit according to the present invention includes a stage 10 provided on a performance space, a plurality of (IR) cameras 100 installed toward the stage 10, an IR A marker 200, and a control unit 400 controlling the camera 100 and tracking the position of the user using the received sensing value.

The camera 100 includes two or more infrared (IR) cameras for photographing a subject using infrared rays (IR). At this time, the plurality of cameras 110 and 120 constituting the camera 100 are installed at positions separated from each other.

Accordingly, the camera 100 can calculate the position of the subject through the difference in the imaging angle of the recognized subject. The algorithm for calculating the position of the object photographed by the multi-cameras is a commercialized technique, which is not described in detail herein.

2, the present invention includes a plurality of cameras 100 installed at multiple angles.

Accordingly, the present invention can more accurately calculate the position of the subject through the plurality of cameras 100.

Meanwhile, in the present invention, the camera can recognize the subject itself, but in order to improve the accuracy of recognition, the infrared marker 200 is recognized by the infrared camera. This will be described in detail again.

The IR marker 200 is a marker attached to a part of the user's body so that the IR camera accurately recognizes the user. The IR marker 200 may include an identification mark composed of a general infrared ray reflective film or the like.

The identification mark may be variously configured according to the characteristics of the IR camera. Preferably, the identification mark may be a mark reflecting a specific color or a mark reflecting a light signal having a frequency of a specific region.

The control unit 400 calculates the precise position and direction of the user by using the imaging data of the camera 100. To this end, the control unit 400 includes a communication module 410, a calculation module 420 ), A control module 410, and a database 440.

The communication module 410 receives the imaging data of the camera 100.

The control module 430 stores the measurement values of the object (user) received from the cameras 100 in the database 440.

The calculation module 420 calculates the position of the object using the measurement values of the camera 100 stored in the database 440 and corrects the position of the object.

The database 440 stores the measurement values received from the camera 100 to calculate the position and direction of the object.

On the other hand, the control module 430 divides the stage 10 into a plurality of regions based on the recognition rates of the respective regions of each camera 100, which will be described later, (100).

That is, when the target object is located in a specific area on the stage 10, the control module 430 does not recognize / track the target object using all installed cameras 100, And recognizes / tracks the target object using only the objects 100.

Hereinafter, a method of inspecting the recognition rates of the cameras 110 and 120 for each of the cameras 110 and 120 on the stage and allocating the cameras according to the recognition rates will be described.

In the object recognition system using the multi-camera unit according to the present invention, the method of checking the recognition rate of each camera is classified into a method using an identification pad and a method using an identification unit. Let's look at it.

First, as shown in FIG. 4, a method of checking the recognition rate of each camera using the identification pad 20 is to check the recognition rate of each camera using the identification pad 20 provided on the object.

When the camera 100 is installed on the stage, the identification pad 20 is configured to set a recognition rate for each camera 100. The identification pad 220 displays a padding that can be placed on the stage it means.

As shown in FIG. 4, the identification pad 20 may be formed in a variety of shapes. However, the identification pad 20 may be divided into regions in a lattice pattern so as to distinguish positions on the identification pad 20, And a cover 220 may be attached.

That is, as shown in FIG. 4, after the cameras 100 are installed in the set position, the identification pad 20 is installed on the stage.

8, the cameras 100 are driven to recognize the respective identification tags 220 on the identification pad 20 (S110, S120).

The control unit 400 receives the identification tag recognition value (sensing value) of each of the cameras 1 to 8 and calculates a position value for each identification tag 210.

At this time, the control unit 400 may calculate the position value of the identification mark 220 according to the measured value of the individual camera, but it is also possible to calculate the position value of the identification mark through the two or more camera measurement values .

This is for determining whether any combination of cameras represents a high position recognition rate in a specific area.

Next, the control unit 400 compares the position values calculated by each camera 100 (or a combination of cameras) with each other, and calculates a position value of the camera unit 100 Set the reflection rate lower.

That is, since the calculation of the object position of the camera unit is basically performed through image analysis, there may be a position where the accuracy is low depending on the distance and direction between the camera and the user.

Accordingly, in the present invention, when the cameras are installed, the positional value calculation accuracy of each camera is tentatively determined. For a position having a low accuracy, a reflection rate of the positional value calculated at the time of system operation is set low, For example.

In this manner, it is also possible to recognize a target object by setting a camera according to the position of the target object in accordance with the recognition rate for each position on the determined stage.

That is, as shown in FIG. 7, the entire area (S0 to S4) on the stage is set separately and a camera having a high recognition rate is set for each area, Can be utilized.

In the example shown in FIG. 7, since the S0 area of the central part has a high recognition rate of all the cameras, it is possible to recognize / track the object using any camera, but the inclination angle is relatively It is preferable to recognize / track the object using a camera with a small position, and the recognition rate for each camera is calculated by the method described above.

In the meantime, as in the embodiment shown in FIG. 4, the recognition rate calculation for each camera region using the identification pad may be somewhat insufficient depending on constraints in the three-dimensional space.

That is, since the actual performer attaches the IR marker 200 to a specific part of the human body and makes a movement including rotation, the identification pad is fixed on the bottom surface, so that the identification mark on the identification pad 20 The camera having a high recognition rate for the IR marker 220 may be lowered in recognition rate depending on the direction and position on the three-dimensional space of the IR marker 200 in an actual performance situation.

Accordingly, another embodiment of the present invention includes a method of checking the recognition rate for each camera using the identification unit 500. [

That is, according to another embodiment of the present invention, as shown in FIG. 5, the identification unit 500 including the identification mark is used instead of attaching the identification mark on the identification pad.

As shown in FIGS. 5 and 6, the identification unit includes a support portion movably settable in a divided region of the identification pad, a rotation plate formed perpendicular to the bottom surface on the support portion, And an identification mark attached to one side of the rotating plate.

That is, the identification unit 500 is configured to move and set each area of the identification pad 20, and the rotary plate to which the identification mark is attached is rotatably provided in a direction perpendicular to the bottom surface.

Accordingly, the identification mark is installed in a similar manner to the performances of the actual performers, so that it is possible to determine whether a camera or a combination of cameras in the actual performance situation has a high recognition rate of the object in the corresponding region.

Further, the administrator can set the rotational speed of the rotary plate differently according to the type of the performance, and check the recognition rate of each camera in the similarity to the actual performance state.

That is, the rotational speed of the rotary plate is set high in a sports performance with high mobility, and the rotational speed of the rotary plate is set low in a performance with low mobility, so that a recognition rate test can be performed in a real performance state and a view condition.

A method for the control unit 400 to check the recognition rate for a corresponding area of each camera using the identification unit 500 is as described above.

It is to be understood that the invention is not limited to the disclosed embodiment, but is capable of many modifications and variations within the scope of the appended claims. It is self-evident.

The present invention relates to an object recognition system using a multi-camera unit, which is implemented to tremble multiple performers using a plurality of (IR) cameras, but to enhance the accuracy of tracker tracking. According to the present invention, The location of a user in the performance space can be identified and tracked. However, since the performance space is divided and the object is recognized / tracked through IR camera combination having a high recognition rate for each area, the position of the performer can be accurately grasped.

100: camera 200: IR marker
400: control unit 410: communication module
420: operation module 430: control module
440: Database 500: Identification unit

Claims (8)

A stage where the performer moves and performs the performance;
A plurality of cameras installed toward the stage for recognizing an identification mark in the performance space;
An IR marker attached to a part of the performer body and recognized by the camera; And
And a control unit receiving the recognized IR marker sensing value from the cameras and recognizing and tracking the position of the performer according to the IR marker sensing value,
Wherein the control unit comprises:
Said stage being divided into a plurality of zones;
Allocating two or more cameras to be used for recognizing and tracking the performer in each zone according to a recognition rate of the cameras for each zone,
The cameras,
The mounting positions being spaced apart from each other:
Wherein the control unit comprises:
A communication module receiving the IR marker sensing value of the camera;
A control module for storing the sensed values received from the cameras in a database;
A calculation module for calculating and correcting the position of the performer by identifying the performer using a sensing value of the camera stored in the database; And
And a database for storing sensing values and measurement values received from the camera,
The recognition rate of the cameras with respect to each of the zones,
Is checked by recognizing the identification mark on the identification unit installed on the stage where the area is divided in the form of a grid:
The identification unit comprising:
A pedestal portion;
A rotating plate provided on the upper part of the receiving unit perpendicularly to the bottom surface;
A driving unit for rotating the rotating plate; And
And an identification mark attached to one side of the rotary plate,
The control module includes:
Driving the cameras to recognize the identification mark provided on the object;
Receiving an identification marker recognition value of each position for each of the cameras;
Calculating a position value of the identification mark according to the recognition value of each camera;
And comparing the calculated position values with each other to determine a recognition rate of each camera with respect to the corresponding area according to a difference from the average value.
The method according to claim 1,
The driving unit includes:
And the rotation plate is rotated according to the rotation speed set according to the performance type.
delete delete delete delete 3. The method according to claim 1 or 2,
The control module includes:
In calculating the position value of the identification mark according to the recognition value of the cameras,
Calculating a position value by a combination of two or more cameras;
And recognizing the recognition rate for the corresponding area by the combination of the cameras.
8. The method of claim 7,
The control module includes:
Wherein a combination of cameras to be used for recognition and tracking of the performer is set for each zone according to the recognition rate of the combination of cameras for each zone.

Images